transcription.page

YouTube video to text

Paste a YouTube link and get the full transcript with clickable timestamps, ready to read, search and save as notes.

YouTube, Instagram and TikTok are detected automatically
No link at hand? Try an example:

Read a YouTube video instead of rewatching it

A lecture, a coding tutorial, a podcast interview: YouTube is full of things worth remembering, but scrubbing back and forth to find one sentence is slow. With the transcript in front of you, you can skim the whole video in a minute, search for the part you need and copy it straight into your notes. Paste the video link here and transcription.page returns the spoken words as clean paragraphs, along with timestamped segments you can click to open the video at that exact moment.

This is handy for studying, for quoting someone accurately in an article, or for checking what was said in an interview without watching it again. If the video already has captions, we use them; otherwise the audio is transcribed with the Whisper speech recognition model.

How to get the transcript of a YouTube video

  1. Copy the YouTube link

    Copy the address from your browser bar, or tap Share and then Copy in the YouTube app.

  2. Paste the link

    Paste it into the box on this page. If the video isn't in English, set its spoken language in Settings.

  3. Use the transcript

    Read it as paragraphs, click a timestamp to jump into the video, or export it as TXT, Markdown or SRT.

Made for studying and note-taking

  • Clickable timestamps

    Each segment links back to the video, so you can check the context of a sentence in one click.

  • Search the whole video

    Type a term and every match is highlighted, which is much faster than scrubbing through a lesson.

  • Summary and key points

    A short summary and key points are extracted from the transcript to help you review what a video covers.

  • Markdown notes

    Export to Markdown with the summary included and paste it into your note-taking app.

  • Copy with timestamps

    Copy the text with its timestamps to reference exact moments in your notes or study guides.

YouTube transcript questions

Does it work with YouTube's automatic captions?

Yes. When a video has captions on YouTube, including automatic ones, we use them because they are already there and quick to fetch. When a video has no captions at all, the audio is transcribed with the Whisper speech recognition model on our server, so you still get a transcript.

Can I transcribe a YouTube video longer than 10 minutes?

Not at the moment. The tool handles videos up to 10 minutes long. Many lessons and interviews are longer, so check the duration before you paste the link. If the creator has published the content as shorter chapters or separate clips, you can transcribe each part on its own.

Can I transcribe private or unlisted videos?

Private videos won't work, because they can only be seen by accounts the owner has invited, and our server has no account. Age-restricted or region-blocked videos may also fail. A video needs to be viewable by anyone who has the link for the transcription to go through.

How do the timestamps work?

The timestamped view splits the transcript into short segments, each with the time it starts in the video. On YouTube, clicking a timestamp opens the video at that moment, which is useful for checking a quote or rewatching a tricky explanation. You can also copy the whole transcript with its timestamps.

Can I use the transcript to take notes for a class?

Yes, that is one of the most common uses. Export the transcript as Markdown, which includes the summary and key points, and paste it into your notes. You can then cut it down, add headings and keep the timestamps for the parts you want to rewatch before an exam.

Will the transcript be translated into English?

No. The transcript is in the language that is spoken in the video. Supported spoken languages are Arabic, French, English, Spanish, German, Italian and Portuguese. Pick the right one in Settings before you start, especially when the video has no captions and has to go through speech recognition.